[Identifying Novel Coronavirus Pneumonia With CT Images: A Deep Learning Approach With Detail Upsampling and Attention Guidance]. / 从CTå›¾åƒä¸­æ£€æµ‹æ–°åž‹å† çŠ¶ç— æ¯’æ„ŸæŸ“å¯¼è‡´çš„è‚ºç‚Žï¼šä¸€ç§ç»†èŠ‚ä¸Šé‡‡æ ·å’Œæ³¨æ„åŠ›å¼•å¯¼çš„æ·±åº¦å­¦ä¹ æ–¹æ³•.

Objective: To construct a deep learning-based target detection method to help radiologists perform rapid diagnosis of lesions in the CT images of patients with novel coronavirus pneumonia (NCP) by restoring detailed information and mining local information. Methods: We present a deep learning approach that integrates detail upsampling and attention guidance. A linear upsampling algorithm based on bicubic interpolation algorithm was adopted to improve the restoration of detailed information within feature maps during the upsampling phase. Additionally, a visual attention mechanism based on vertical and horizontal spatial dimensions embedded in the feature extraction module to enhance the capability of the object detection algorithm to represent key information related to NCP lesions. Results: Experimental results on the NCP dataset showed that the detection method based on the detail upsampling algorithm improved the recall rate by 1.07% compared with the baseline model, with the AP50 reaching 85.14%. After embedding the attention mechanism in the feature extraction module, 86.13% AP50, 73.92% recall, and 90.37% accuracy were achieved, which were better than those of the popular object detection models. Conclusion: The feature information mining of CT images based on deep learning can further improve the lesion detection ability. The proposed approach helps radiologists rapidly identify NCP lesions on CT images and provides an important clinical basis for early intervention and high-intensity monitoring of NCP patients.

Point-of-care lung ultrasound predicts hyperferritinemia and hospitalization, but not elevated troponin in SARS-CoV-2 viral pneumonitis in children.

SARS-CoV-2 often causes viral pneumonitis, hyperferritinemia, elevations in D-dimer, lactate dehydrogenase (LDH), transaminases, troponin, CRP, and other inflammatory markers. Lung ultrasound is increasingly used to diagnose and stratify viral pneumonitis severity. We retrospectively reviewed 427 visits in patients aged 14 days to 21 years who had had a point-of-care lung ultrasound in our pediatric emergency department from 30/November/2019 to 14/August/2021. Lung ultrasounds were categorized using a 6-point ordinal scale. Lung ultrasound abnormalities predicted increased hospitalization with a threshold effect. Increasingly abnormal laboratory values were associated with decreased discharge from the ED and increased admission to the ward and ICU. Among patients SARS-CoV-2 positive patients ferritin, LDH, and transaminases, but not CRP or troponin were significantly associated with abnormalities on lung ultrasound and also with threshold effects. This effect was not demonstrated in SARS-CoV-2 negative patients. D-Dimer, CRP, and troponin were sometimes elevated even when the lung ultrasound was normal.

Enhancing pediatric pneumonia diagnosis through masked autoencoders.

Pneumonia, an inflammatory lung condition primarily triggered by bacteria, viruses, or fungi, presents distinctive challenges in pediatric cases due to the unique characteristics of the respiratory system and the potential for rapid deterioration. Timely diagnosis is crucial, particularly in children under 5, who have immature immune systems, making them more susceptible to pneumonia. While chest X-rays are indispensable for diagnosis, challenges arise from subtle radiographic findings, varied clinical presentations, and the subjectivity of interpretations, especially in pediatric cases. Deep learning, particularly transfer learning, has shown promise in improving pneumonia diagnosis by leveraging large labeled datasets. However, the scarcity of labeled data for pediatric chest X-rays presents a hurdle in effective model training. To address this challenge, we explore the potential of self-supervised learning, focusing on the Masked Autoencoder (MAE). By pretraining the MAE model on adult chest X-ray images and fine-tuning the pretrained model on a pediatric pneumonia chest X-ray dataset, we aim to overcome data scarcity issues and enhance diagnostic accuracy for pediatric pneumonia. The proposed approach demonstrated competitive performance an AUC of 0.996 and an accuracy of 95.89% in distinguishing between normal and pneumonia. Additionally, the approach exhibited high AUC values (normal: 0.997, bacterial pneumonia: 0.983, viral pneumonia: 0.956) and an accuracy of 93.86% in classifying normal, bacterial pneumonia, and viral pneumonia. This study also investigated the impact of different masking ratios during pretraining and explored the labeled data efficiency of the MAE model, presenting enhanced diagnostic capabilities for pediatric pneumonia.

Radiographic findings of adenoviral pneumonia in children.

OBJECTIVE: Adenovirus pneumonia is a common cause of community-acquired pneumonia in children and can mimic bacterial pneumonia, but there are few publications on its radiographic features. This study has evaluated the chest radiography findings of community-acquired adenovirus pneumonia in children. The frequency of radiological findings mimicking bacterial pneumonia was investigated. The clinical features of patients with adenovirus pneumonia possessing radiological findings mimicking bacterial pneumonia were also evaluated. MATERIALS AND METHODS: The chest radiographs of patients diagnosed with adenovirus pneumonia were retrospectively reviewed. The chest radiographs were interpreted independently by a pediatric infectious disease specialist and a pediatric radiologist. Chest radiography findings mimicking bacterial pneumonia (bacterial-like) were specified as consolidation +/- pleural effusion. Other findings on chest radiography or a completely normal chest X-ray were specified as findings that were compatible with "typical viral pneumonia". RESULTS: A total of 1407 patients were positive for adenovirus with respiratory multiplex PCR. The 219 patients who met the study criteria were included in the study. Chest radiographs were normal in 58 (26.5 %) patients. The chest radiograph findings mimicked bacterial pneumonia in 41 (18.7 %) patients. CONCLUSION: Adenovirus pneumonia occurs predominantly in children aged five years and younger, as with other viral pneumonias. The radiographic findings in adenovirus pneumonia are predominantly those seen in viral pneumonia. Increasing age and positivity for only adenovirus without other viruses on respiratory multiplex PCR were associated with the chest radiograph being more likely to be "bacterial-like". Adenovirus may lead to lobar/segmental consolidation at a rate that is not very rare.

PulmoNet: a novel deep learning based pulmonary diseases detection model.

Pulmonary diseases are various pathological conditions that affect respiratory tissues and organs, making the exchange of gas challenging for animals inhaling and exhaling. It varies from gentle and self-limiting such as the common cold and catarrh, to life-threatening ones, such as viral pneumonia (VP), bacterial pneumonia (BP), and tuberculosis, as well as a severe acute respiratory syndrome, such as the coronavirus 2019 (COVID-19). The cost of diagnosis and treatment of pulmonary infections is on the high side, most especially in developing countries, and since radiography images (X-ray and computed tomography (CT) scan images) have proven beneficial in detecting various pulmonary infections, many machine learning (ML) models and image processing procedures have been utilized to identify these infections. The need for timely and accurate detection can be lifesaving, especially during a pandemic. This paper, therefore, suggested a deep convolutional neural network (DCNN) founded image detection model, optimized with image augmentation technique, to detect three (3) different pulmonary diseases (COVID-19, bacterial pneumonia, and viral pneumonia). The dataset containing four (4) different classes (healthy (10,325), COVID-19 (3,749), BP (883), and VP (1,478)) was utilized as training/testing data for the suggested model. The model's performance indicates high potential in detecting the three (3) classes of pulmonary diseases. The model recorded average detection accuracy of 94%, 95.4%, 99.4%, and 98.30%, and training/detection time of about 60/50 s. This result indicates the proficiency of the suggested approach when likened to the traditional texture descriptors technique of pulmonary disease recognition utilizing X-ray and CT scan images. This study introduces an innovative deep convolutional neural network model to enhance the detection of pulmonary diseases like COVID-19 and pneumonia using radiography. This model, notable for its accuracy and efficiency, promises significant advancements in medical diagnostics, particularly beneficial in developing countries due to its potential to surpass traditional diagnostic methods.

Caracterización metabólica de los cambios pulmonares estructurales en pacientes con hallazgos incidentales sugestivos de neumonía por COVID-19 en estudios 18F-FDG PET/CT. Perspectivas fisiopatológicas de imágenes multimodales obtenidas durante la pandemia / Metabolic characterization of structural lung changes in patients with findings suggestive of incidental COVID-19 pneumonia on 18F-FDG PET/CT: Pathophysiological insights from multimodal images obtained during the pandemic

Objetivo Evaluar la captación metabólica de diferentes signos tomográficos observados en pacientes con hallazgos estructurales incidentales sugestivos de neumonía por COVID-19 mediante PET/TC con 18F-FDG. Material y métodos Se analizaron retrospectivamente 596 estudios PET/TC realizados desde el 21 de febrero de 2020 hasta el 17 de abril de 2020. Tras excluir 37 exploraciones (trazadores PET diferentes a la 18F-FDG y estudios cerebrales), se evaluó la actividad metabólica de varios cambios estructurales integrados en la puntuación CO-RADS mediante el SUVmáx de estudios multimodales con 18F-FDG. Resultados Se incluyeron 43 pacientes r COVID-19 en la 18F-FDG PET/TC (edad media: 68±12,3 años, 22 varones). Los valores de SUVmáx fueron mayores en los pacientes con categorías CO-RADS 5-6 respecto a los de categorías CO-RADS inferiores (6,1±3,0 vs. 3,6±2,1, p=0,004). En los pacientes con CO-RADS 5-6, las opacidades en vidrio deslustrado, la bilateralidad y las consolidaciones mostraron valores de SUVmáx más elevados (valores de la p de 0,01, 0,02 y 0,01, respectivamente). La distribución parcheada y el patrón crazy paving también se asociaron a valores de SUVmáx más elevados (valores de p de 0,002 y 0,01). Tras el análisis multivariable, el SUVmáx se asoció significativamente con un diagnóstico estructural positivo de neumonía por COVID-19 (odds ratio=0,63, intervalo de confianza del 95%=0,41-0,90; p=0,02). La curva ROC del modelo de regresión destinado a confirmar o descartar el diagnóstico estructural de neumonía por COVID-19 mostró un AUC de 0,77 (error estándar=0,072; p=0,003). Conclusiones En aquellos pacientes remitidos a 18F-FDG PET/TC por indicaciones oncológicas y no oncológicas estándar (43/559; 7,7%) durante la pandemia, la obtención de imágenes multimodales es una herramienta útil durante la detección incidental de neumonía (AU)

Purpose To evaluate the metabolic uptake of different tomographic signs observed in patients with incidental structural findings suggestive of COVID-19 pneumonia through 18F-FDG PET/CT. Material and methods We retrospectively analyzed 596 PET/CT studies performed from February 21, 2020 to April 17, 2020. After excluding 37 scans (non-18F-FDG PET tracers and brain studies), we analyzed the metabolic activity of several structural changes integrated in the CO-RADS score using the SUVmax of multimodal studies with 18F-FDG. Results Forty-three patients with 18F-FDG PET/CT findings suggestive of COVID-19 pneumonia were included (mean age: 68±12.3 years, 22 male). SUVmax values were higher in patients with CO-RADS categories 5–6 than in those with lower CO-RADS categories (6.1±3.0 vs. 3.6±2.1, p=0.004). In patients with CO-RADS 5–6, ground-glass opacities, bilaterality and consolidations exhibited higher SUVmax values (p-values of 0.01, 0.02 and 0.01, respectively). Patchy distribution and crazy paving pattern were also associated with higher SUVmax (p-values of 0.002 and 0.01). After multivariate analysis, SUVmax was significantly associated with a positive structural diagnosis of COVID-19 pneumonia (odds ratio=0.63, 95% confidence interval=0.41–0.90; p=0.02). The ROC curve of the regression model intended to confirm or rule out the structural diagnosis of COVID-19 pneumonia showed an AUC of 0.77 (standard error=0.072, p=0.003). Conclusions In those patients referred for standard oncologic and non-oncologic indications (43/559; 7.7%) during pandemic, imaging with 18F-FDG PET/CT is a useful tool during incidental detection of COVID-19 pneumonia. Several CT findings characteristic of COVID-19 pneumonia, specifically those included in diagnostic CO-RADS scores (5–6), were associated with higher SUVmax values (AU)

[Chinese expert consensus on the imaging diagnosis of severe pneumonia of influenza A (H1N1) flu].

In March 2009, influenza A(H1N1) flu broke out and spread rapidly worldwide, and it has been circulating in local areas with various scales since then. Particularly, the outbreak and prevalence have occurred in China during 2023 extensively. At present, there is an absence of unified consensus on imaging diagnosis of severe influenza A (H1N1) flu pneumonia, which is not conducive to the standardized imaging diagnosis and clinical practice. Chinese experts including the Infection and Inflammatory Radiology Committee of the Chinese Research Hospital Association jointly formulate this consensus based on numerous references related to influenza A (H1N1) flu, meanwhile combining the methodological requirements of evidence-based medicine for guideline and standard formulation. This consensus aims to form a consensus on the diagnostic evidence, recommended imaging methods, diagnostic standard and differential diagnosis of severe influenza A(H1N1) flu pneumonia, and it is ought to provide clear diagnostic information and basis for relevant professional physicians and guide the clinical diagnosis and treatment of severe pneumonia caused by influenza A(H1N1) flu.

Pneumonia-Plus: a deep learning model for the classification of bacterial, fungal, and viral pneumonia based on CT tomography.

OBJECTIVES: This study aims to develop a deep learning algorithm, Pneumonia-Plus, based on computed tomography (CT) images for accurate classification of bacterial, fungal, and viral pneumonia. METHODS: A total of 2763 participants with chest CT images and definite pathogen diagnosis were included to train and validate an algorithm. Pneumonia-Plus was prospectively tested on a nonoverlapping dataset of 173 patients. The algorithm's performance in classifying three types of pneumonia was compared to that of three radiologists using the McNemar test to verify its clinical usefulness. RESULTS: Among the 173 patients, area under the curve (AUC) values for viral, fungal, and bacterial pneumonia were 0.816, 0.715, and 0.934, respectively. Viral pneumonia was accurately classified with sensitivity, specificity, and accuracy of 0.847, 0.919, and 0.873. Three radiologists also showed good consistency with Pneumonia-Plus. The AUC values of bacterial, fungal, and viral pneumonia were 0.480, 0.541, and 0.580 (radiologist 1: 3-year experience); 0.637, 0.693, and 0.730 (radiologist 2: 7-year experience); and 0.734, 0.757, and 0.847 (radiologist 3: 12-year experience), respectively. The McNemar test results for sensitivity showed that the diagnostic performance of the algorithm was significantly better than that of radiologist 1 and radiologist 2 (p < 0.05) in differentiating bacterial and viral pneumonia. Radiologist 3 had a higher diagnostic accuracy than the algorithm. CONCLUSIONS: The Pneumonia-Plus algorithm is used to differentiate between bacterial, fungal, and viral pneumonia, which has reached the level of an attending radiologist and reduce the risk of misdiagnosis. The Pneumonia-Plus is important for appropriate treatment and avoiding the use of unnecessary antibiotics, and provide timely information to guide clinical decision-making and improve patient outcomes. CLINICAL RELEVANCE STATEMENT: Pneumonia-Plus algorithm could assist in the accurate classification of pneumonia based on CT images, which has great clinical value in avoiding the use of unnecessary antibiotics, and providing timely information to guide clinical decision-making and improve patient outcomes. KEY POINTS: • The Pneumonia-Plus algorithm trained from data collected from multiple centers can accurately identify bacterial, fungal, and viral pneumonia. • The Pneumonia-Plus algorithm was found to have better sensitivity in classifying viral and bacterial pneumonia in comparison to radiologist 1 (5-year experience) and radiologist 2 (7-year experience). • The Pneumonia-Plus algorithm is used to differentiate between bacterial, fungal, and viral pneumonia, which has reached the level of an attending radiologist.

Lung ultrasound score severity cut-off points in COVID-19 pneumonia. A systematic review and validating cohort / Puntos de corte de gravedad del Lung Ultrasound Score en la neumonía COVID-19. Revisión sistemática de la literatura y cohorte de validación

Objectives Our purpose was to establish different cut-off points based on the lung ultrasound score (LUS) to classify COVID-19 pneumonia severity. Methods Initially, we conducted a systematic review among previously proposed LUS cut-off points. Then, these results were validated by a single-centre prospective cohort study of adult patients with confirmed SARS-CoV-2 infection. Studied variables were poor outcome (ventilation support, intensive care unit admission or 28-days mortality) and 28-days mortality. Results From 510 articles, 11 articles were included. Among the cut-off points proposed in the articles included, only the LUS>15 cut-off point could be validated for its original endpoint, demonstrating also the strongest relation with poor outcome (odds ratio [OR]=3.636, confidence interval [CI] 1.411–9.374). Regarding our cohort, 127 patients were admitted. In these patients, LUS was statistically associated with poor outcome (OR=1.303, CI 1.137–1.493), and with 28-days mortality (OR=1.024, CI 1.006–1.042). LUS>15 showed the best diagnostic performance when choosing a single cut-off point in our cohort (area under the curve 0.650). LUS≤7 showed high sensitivity to rule out poor outcome (0.89, CI 0.695–0.955), while LUS>20 revealed high specificity to predict poor outcome (0.86, CI 0.776–0.917). Conclusions LUS is a good predictor of poor outcome and 28-days mortality in COVID-19. LUS≤7 cut-off point is associated with mild pneumonia, LUS 8–20 with moderate pneumonia and ≥20 with severe pneumonia. If a single cut-off point were used, LUS>15 would be the point which better discriminates mild from severe disease (AU)

Objetivos Establecer diferentes puntos de corte basados en el Lung Ultrasound Score (LUS) para clasificar la gravedad de la neumonía COVID-19. Métodos Inicialmente, realizamos una revisión sistemática entre los puntos de corte LUS propuestos previamente. Estos resultados fueron validados por una cohorte prospectiva unicéntrica de pacientes adultos con infección confirmada por SARS-CoV-2. Las variables analizadas fueron la mala evolución y la mortalidad a los 28 días. Resultados De 510 artículos, se incluyeron 11. Entre los puntos de corte propuestos en los artículos incluidos, solo LUS>15 pudo ser validado para su objetivo original, demostrando también la relación más fuerte con mala evolución (odds ratio [OR]=3,636, intervalo de confianza [IC] 1,411-9,374). Respecto a nuestra cohorte, se incluyeron 127 pacientes. En estos pacientes, el LUS se asoció estadísticamente con mala evolución (OR=1,303, IC 1,137-1,493) y con mortalidad a los 28 días (OR=1,024, IC 1,006-1,042). LUS>15 mostró el mejor rendimiento diagnóstico al elegir un único punto de corte en nuestra cohorte (área bajo la curva 0,650). LUS≤7 mostró una alta sensibilidad para descartar mal resultado (0,89, IC 0,695-0,955), mientras que LUS>20 reveló gran especificidad para predecir mala evolución (0,86, IC 0,776-0,917). Conclusiones LUS es un buen predictor de mala evolución y mortalidad a 28 días en COVID-19. LUS≤7 se asocia con neumonía leve, LUS 8-20 con neumonía moderada y ≥20 con neumonía grave. Si se utilizara un único punto de corte, LUS>15 sería el que mejor discriminaría la enfermedad leve de la grave (AU)

An efficient, lightweight MobileNetV2-based fine-tuned model for COVID-19 detection using chest X-ray images.

In recent years, deep learning's identification of cancer, lung disease and heart disease, among others, has contributed to its rising popularity. Deep learning has also contributed to the examination of COVID-19, which is a subject that is currently the focus of considerable scientific debate. COVID-19 detection based on chest X-ray (CXR) images primarily depends on convolutional neural network transfer learning techniques. Moreover, the majority of these methods are evaluated by using CXR data from a single source, which makes them prohibitively expensive. On a variety of datasets, current methods for COVID-19 detection may not perform as well. Moreover, most current approaches focus on COVID-19 detection. This study introduces a rapid and lightweight MobileNetV2-based model for accurate recognition of COVID-19 based on CXR images; this is done by using machine vision algorithms that focused largely on robust and potent feature-learning capabilities. The proposed model is assessed by using a dataset obtained from various sources. In addition to COVID-19, the dataset includes bacterial and viral pneumonia. This model is capable of identifying COVID-19, as well as other lung disorders, including bacterial and viral pneumonia, among others. Experiments with each model were thoroughly analyzed. According to the findings of this investigation, MobileNetv2, with its 92% and 93% training validity and 88% precision, was the most applicable and reliable model for this diagnosis. As a result, one may infer that this study has practical value in terms of giving a reliable reference to the radiologist and theoretical significance in terms of establishing strategies for developing robust features with great presentation ability.

A Real Time Method for Distinguishing COVID-19 Utilizing 2D-CNN and Transfer Learning.

Rapid identification of COVID-19 can assist in making decisions for effective treatment and epidemic prevention. The PCR-based test is expert-dependent, is time-consuming, and has limited sensitivity. By inspecting Chest R-ray (CXR) images, COVID-19, pneumonia, and other lung infections can be detected in real time. The current, state-of-the-art literature suggests that deep learning (DL) is highly advantageous in automatic disease classification utilizing the CXR images. The goal of this study is to develop models by employing DL models for identifying COVID-19 and other lung disorders more efficiently. For this study, a dataset of 18,564 CXR images with seven disease categories was created from multiple publicly available sources. Four DL architectures including the proposed CNN model and pretrained VGG-16, VGG-19, and Inception-v3 models were applied to identify healthy and six lung diseases (fibrosis, lung opacity, viral pneumonia, bacterial pneumonia, COVID-19, and tuberculosis). Accuracy, precision, recall, f1 score, area under the curve (AUC), and testing time were used to evaluate the performance of these four models. The results demonstrated that the proposed CNN model outperformed all other DL models employed for a seven-class classification with an accuracy of 93.15% and average values for precision, recall, f1-score, and AUC of 0.9343, 0.9443, 0.9386, and 0.9939. The CNN model equally performed well when other multiclass classifications including normal and COVID-19 as the common classes were considered, yielding accuracy values of 98%, 97.49%, 97.81%, 96%, and 96.75% for two, three, four, five, and six classes, respectively. The proposed model can also identify COVID-19 with shorter training and testing times compared to other transfer learning models.

[Analysis of chest imaging features of novel coronavirus pneumonia, bacterial pneumonia and viral pneumonia].

OBJECTIVE: To investigate and summarize the chest CT imaging features of patients with novel coronavirus pneumonia (COVID-19), bacterial pneumonia and other viral pneumonia. METHODS: Chest CT data of 102 patients with pulmonary infection due to different etiologies were retrospectively analyzed, including 36 patients with COVID-19 admitted to Hainan Provincial People's Hospital and the Second Affiliated Hospital of Hainan Medical University from December 2019 to March 2020, 16 patients with other viral pneumonia admitted to Hainan Provincial People's Hospital from January 2018 to February 2020, and 50 patients with bacterial pneumonia admitted to Haikou Affiliated Hospital of Central South University Xiangya School of Medicine from April 2018 to May 2020. Two senior radiologists and two senior intensive care physicians were participated to evaluated the extent of lesions involvement and imaging features of the first chest CT after the onset of the disease. RESULTS: Bilateral pulmonary lesions were more common in patients with COVID-19 and other viral pneumonia, and the incidence was significantly higher than that of bacterial pneumonia (91.6%, 75.0% vs. 26.0%, P < 0.05). Compared with other viral pneumonia and COVID-19, bacterial pneumonia was mainly characterized by single-lung and multi-lobed lesion (62.0% vs. 18.8%, 5.6%, P < 0.05), accompanied by pleural effusion and lymph node enlargement. The proportion of ground-glass opacity in the lung tissues of patients with COVID-19 was 97.2%, that of patients with other viral pneumonia was 56.2%, and that of patients with bacterial pneumonia was only 2.0% (P < 0.05). The incidence rate of lung tissue consolidation (25.0%, 12.5%), air bronchial sign (13.9%, 6.2%) and pleural effusion (16.7%, 37.5%) in patients with COVID-19 and other viral pneumonia were significantly lower than those in patients with bacterial pneumonia (62.0%, 32.0%, 60.0%, all P < 0.05), paving stone sign (22.2%, 37.5%), fine mesh sign (38.9%, 31.2%), halo sign (11.1%, 25.0%), ground-glass opacity with interlobular septal thickening (30.6%, 37.5%), bilateral patchy pattern/rope shadow (80.6%, 50.0%) etc. were significantly higher than those of bacterial pneumonia (2.0%, 4.0%, 2.0%, 0%, 22.0%, all P < 0.05). The incidence of local patchy shadow in patients with COVID-19 was only 8.3%, significantly lower than that in patients with other viral pneumonia and bacterial pneumonia (8.3% vs. 68.8%, 50.0%, P < 0.05). There was no significant difference in the incidence of peripheral vascular shadow thickening in patients with COVID-19, other viral pneumonia and bacterial pneumonia (27.8%, 12.5%, 30.0%, P > 0.05). CONCLUSIONS: The probability of ground-glass opacity, paving stone and grid shadow in chest CT of patients with COVID-19 was significantly higher than those of bacterial pneumonia, and it was more common in the lower lungs and lateral dorsal segment. In other patients with viral pneumonia, ground-glass opacity was distributed in both upper and lower lungs. Bacterial pneumonia is usually characterized by single lung consolidation, distributed in lobules or large lobes and accompanied by pleural effusion.

COVID-19 en Pediatría: descripción clínica y microbiológica de los pacientes ingresados en un hospital terciario / COVID-19 in pediatrics: clinical and microbiological description of patients admitted to a tertiary hospital

Introducción: desde el inicio de la pandemia por el virus SARS-CoV-2 una de las grandes cuestiones que se ha formulado es qué papel desempeñan los niños en el control y manejo de la pandemia y cómo esta les ha afectado. Hay mucha bibliografía acerca de los síntomas y complicaciones que puede presentar esta población, pero poca de cómo ha sido el curso clínico de la infección en los niños ingresados en hospitales de tercer nivel y su impacto asistencial. Material y métodos: se han analizado descriptivamente las historias clínicas de los niños ingresados en el Hospital General Doctor Balmis de Alicante (España) desde enero de 2020 hasta julio de 2022. Se han analizado paralelamente los datos microbiológicos del SARS-CoV-2, variantes y linajes, desde agosto de 2021 hasta agosto de 2022. Resultados: se analizaron un total de 114 niños ingresados con diagnóstico de infección por SARS-CoV-2, de los cuales la mayoría tenían menos de 12 meses y eran de procedencia española. Los ingresos se distribuyeron de forma cronológica siguiendo un modelo de “olas”, siendo el motivo más frecuente la constatación del virus SARS-CoV-2 en las pruebas realizadas. El tratamiento que más frecuentemente recibieron durante el ingreso fueron los antibióticos orales. La mayor parte de los niños no tenían comorbilidades y no desarrollaron complicaciones. La variante mayoritaria fue ómicron y el linaje el BA.1. Discusión: los lactantes parecen ser más vulnerables a la infección por SARS-CoV-2 y las manifestaciones clínicas en este grupo de edad conllevan mayor probabilidad de ingreso. El desarrollo de complicaciones, necesidad de oxigenoterapia, ventilación mecánica e ingreso en UCI es mínimo en población pediátrica. El manejo de la infección difiere sustancialmente con el de los adultos, lo que se corresponde con tratamientos menos agresivos (AU)

Introduction: since the beginning of the SARS-CoV-2 pandemic, one of the main questions that has been asked is what role children play in the control and management of the pandemic and how it has affected them. There is much literature on the symptoms and complications that this population may have, but little on the clinical course of the infection in children admitted to tertiary hospitals and its impact on health care.Material and methods: the clinical histories of children admitted to the Hospital General Doctor Balmis (Alicante, Spain) from January 2020 to July 2022 were analyzed descriptively. At the same time, microbiological data on SARS-CoV-2, variants and lineages were analyzed from August 2021 to August 2022.Results: a total of 114 children admitted were analyzed, most of whom were younger than 12 months and from Spain. Admissions were distributed chronologically following a 'wave' pattern, the most frequent reason being the finding of SARS-CoV-2 virus in the tests performed. The most common treatment received during admission was oral antibiotics. Most of the children had no comorbidities and did not develop complications.Discussion: infants seem to be more vulnerable to SARS-CoV-2 infection, and clinical manifestations in this age group are more likely to lead to admission. The development of complications, need for oxygen therapy, mechanical ventilation and admission to the ICU is minimal in the pediatric population. The management of infection differs substantially from that of adults, which corresponds to less aggressive treatment. (AU)

Automated grading of chest x-ray images for viral pneumonia with convolutional neural networks ensemble and region of interest localization.

Following its initial identification on December 31, 2019, COVID-19 quickly spread around the world as a pandemic claiming more than six million lives. An early diagnosis with appropriate intervention can help prevent deaths and serious illness as the distinguishing symptoms that set COVID-19 apart from pneumonia and influenza frequently don't show up until after the patient has already suffered significant damage. A chest X-ray (CXR), one of many imaging modalities that are useful for detection and one of the most used, offers a non-invasive method of detection. The CXR image analysis can also reveal additional disorders, such as pneumonia, which show up as anomalies in the lungs. Thus these CXRs can be used for automated grading aiding the doctors in making a better diagnosis. In order to classify a CXR image into the Negative for Pneumonia, Typical, Indeterminate, and Atypical, we used the publicly available CXR image competition dataset SIIM-FISABIO-RSNA COVID-19 from Kaggle. The suggested architecture employed an ensemble of EfficientNetv2-L for classification, which was trained via transfer learning from the initialised weights of ImageNet21K on various subsets of data (Code for the proposed methodology is available at: https://github.com/asadkhan1221/siim-covid19.git). To identify and localise opacities, an ensemble of YOLO was combined using Weighted Boxes Fusion (WBF). Significant generalisability gains were made possible by the suggested technique's addition of classification auxiliary heads to the CNN backbone. The suggested method improved further by utilising test time augmentation for both classifiers and localizers. The results for Mean Average Precision score show that the proposed deep learning model achieves 0.617 and 0.609 on public and private sets respectively and these are comparable to other techniques for the Kaggle dataset.

CXR-Net: A Multitask Deep Learning Network for Explainable and Accurate Diagnosis of COVID-19 Pneumonia From Chest X-Ray Images.

Accurate and rapid detection of COVID-19 pneumonia is crucial for optimal patient treatment. Chest X-Ray (CXR) is the first-line imaging technique for COVID-19 pneumonia diagnosis as it is fast, cheap and easily accessible. Currently, many deep learning (DL) models have been proposed to detect COVID-19 pneumonia from CXR images. Unfortunately, these deep classifiers lack the transparency in interpreting findings, which may limit their applications in clinical practice. The existing explanation methods produce either too noisy or imprecise results, and hence are unsuitable for diagnostic purposes. In this work, we propose a novel explainable CXR deep neural Network (CXR-Net) for accurate COVID-19 pneumonia detection with an enhanced pixel-level visual explanation using CXR images. An Encoder-Decoder-Encoder architecture is proposed, in which an extra encoder is added after the encoder-decoder structure to ensure the model can be trained on category samples. The method has been evaluated on real world CXR datasets from both public and private sources, including healthy, bacterial pneumonia, viral pneumonia and COVID-19 pneumonia cases. The results demonstrate that the proposed method can achieve a satisfactory accuracy and provide fine-resolution activation maps for visual explanation in the lung disease detection. Compared to current state-of-the-art visual explanation methods, the proposed method can provide more detailed, high-resolution, visual explanation for the classification results. It can be deployed in various computing environments, including cloud, CPU and GPU environments. It has a great potential to be used in clinical practice for COVID-19 pneumonia diagnosis.

Diagnostic Performance in Differentiating COVID-19 from Other Viral Pneumonias on CT Imaging: Multi-Reader Analysis Compared with an Artificial Intelligence-Based Model.

Growing evidence suggests that artificial intelligence tools could help radiologists in differentiating COVID-19 pneumonia from other types of viral (non-COVID-19) pneumonia. To test this hypothesis, an R-AI classifier capable of discriminating between COVID-19 and non-COVID-19 pneumonia was developed using CT chest scans of 1031 patients with positive swab for SARS-CoV-2 (n = 647) and other respiratory viruses (n = 384). The model was trained with 811 CT scans, while 220 CT scans (n = 151 COVID-19; n = 69 non-COVID-19) were used for independent validation. Four readers were enrolled to blindly evaluate the validation dataset using the CO-RADS score. A pandemic-like high suspicion scenario (CO-RADS 3 considered as COVID-19) and a low suspicion scenario (CO-RADS 3 considered as non-COVID-19) were simulated. Inter-reader agreement and performance metrics were calculated for human readers and R-AI classifier. The readers showed good agreement in assigning CO-RADS score (Gwet's AC2 = 0.71, p < 0.001). Considering human performance, accuracy = 78% and accuracy = 74% were obtained in the high and low suspicion scenarios, respectively, while the AI classifier achieved accuracy = 79% in distinguishing COVID-19 from non-COVID-19 pneumonia on the independent validation dataset. The R-AI classifier performance was equivalent or superior to human readers in all comparisons. Therefore, a R-AI classifier may support human readers in the difficult task of distinguishing COVID-19 from other types of viral pneumonia on CT imaging.